Hi everyone,

Please join us in supporting Heather Doig at the public presentation of her PhD oral thesis defence, later today. Details are as follows:

Faculty of Engineering

Thesis Public Presentation [https://d31hzlhk6di2h5.cloudfront.net/20260421/44/a0/ac/85/83de99ae1318da0ad...] Heather Doig will present her thesis titled Benthic Visual Recognition in an Annotation-poor Domain.

Please join us in celebrating this significant milestone in Heather’s academic journey, which recognises her sustained commitment and extensive research in this field.

Date: Wednesday, 29 April 2026

Time: 04:00 PM (AEDT)

Venue: ACFR J04, Level 2 Seminar Area (Rose Street Buildinghttps://url.au.m.mimecastprotect.com/s/h00kCQnMBZf3g05zEunU6TGAvLp?domain=t.e2ma.net)

Online: https://uni-sydney.zoom.us/j/87341223912https://url.au.m.mimecastprotect.com/s/FnuVCROND2uRo2A7kFycRT1uunG?domain=t.e2ma.net [https://d31hzlhk6di2h5.cloudfront.net/20260421/92/f7/f0/97/784c6220145aebd55...] Abstract:

The ocean is a vital natural resource, providing food, transportation, energy, and recreation. Anthropogenic and other stresses are impacting benthic communities and habitats residing on or near the seafloor. Biodiversity monitoring using benthic imagery provides insight into how widespread or localised stresses are impacting the ocean, but manual annotation of this imagery remains a significant bottleneck, requiring up to 8 hours of expert labour per image. While machine learning (ML) offers a path toward automation, developing robust models is hindered by the scarcity of diverse training datasets and by the unique environmental challenges of the underwater domain, such as light attenuation and domain shift. This thesis addresses these limitations by investigating whether alternative data sources, such as weakly annotated data and synthetically generated imagery, can compensate for the lack of expert-labelled data. By developing a framework that integrates specialised training pipelines with unsupervised domain adaptation and model selection, this work demonstrates that high-performing species detectors can be trained with minimal to no human annotation. These contributions ultimately provide an applied solution that performs at a level comparable to fully supervised models, enabling the timely and automated generation of ecological insights needed to manage the benthic environment.

Bio:

Heather Doig completed her PhD (currently under examination) at the ACFR in 2025, during which she developed new machine learning approaches for environmental and ecological monitoring of the seafloor. Her research spans domain adaptation, synthetic data generation, and methods for learning from weak or sparse annotations in data‑limited environments. She holds a Master of Data Science from the University of Sydney and a Bachelor of Engineering from the University of Melbourne. Prior to academia, Heather worked in technology and operations management at Macquarie Bank and at ReachOut Australia. [https://d31hzlhk6di2h5.cloudfront.net/20260421/2e/8d/c7/1c/1c70baef8b350e384...]

[Web Site]https://url.au.m.mimecastprotect.com/s/ZzZsCVARKgC5mGDOLu5fATE-bxZ?domain=t.e2ma.net [LinkedIn]https://url.au.m.mimecastprotect.com/s/cH0ECWLVXkUPZJAlgC2hQToMEOI?domain=t.e2ma.net [X]https://url.au.m.mimecastprotect.com/s/aeyqCXLW2mUqjwxpysoiMTWy-NU?domain=t.e2ma.net [YouTube]https://url.au.m.mimecastprotect.com/s/K-ckCYW8NocNmrzGJT6sYTxBe9p?domain=t.e2ma.net

Copyright © 2026

The University of Sydney

Please add acfr.admin@sydney.edu.aumailto:acfr.admin@sydney.edu.au to your address book or senders safe list to make sure you continue to see our emails in the future.

Cricos Code 00026A TEQSA PRV12057 Disclaimerhttps://url.au.m.mimecastprotect.com/s/N1frCZY1NqiDAJ3OVT6t8TBKu9U?domain=t.e2ma.net | Privacy statementhttps://url.au.m.mimecastprotect.com/s/tGoaC1WLPxckxV7vDuounTV3dKp?domain=t.e2ma.net |

Managehttps://url.au.m.mimecastprotect.com/s/eW7-CMwGxOtRDNQE0FOHXT8K9eh?domain=app.e2ma.net your preferences | Opt Outhttps://url.au.m.mimecastprotect.com/s/WIiVCNLJyQUEJ42vrF8IlTybOGN?domain=t.e2ma.net using TrueRemove™ Got this as a forward? Sign uphttps://url.au.m.mimecastprotect.com/s/ZqlECOMKzVT0lW6q9fYSKTGD3vZ?domain=app.e2ma.net/ to receive our future emails. View this email onlinehttps://url.au.m.mimecastprotect.com/s/DS56CP7LAXfo9p7yrFRTmTxCGhS?domain=t.e2ma.net.

Rose Street Building J04 Level 2 | Darlington, 2008 AU

Best regards,

Sabrina

Sabrina Asri | Senior Admin Officer The University of Sydney Faculty of Engineering, Australian Centre for Robotics Rose Street Building J04 | The University of Sydney | NSW | 2006 +61 2 9351 7126 | sabrina.asri@sydney.edu.aumailto:sabrina.asri@sydney.edu.au | sydney.edu.auhttp://sydney.edu.au/

[A black background with a black square AI-generated content may be incorrect.]

CRICOS 00026A TEQSA PRV12057 This email plus any attachments to it are confidential. Any unauthorised use is strictly prohibited. If you receive this email in error, please delete it and any attachments. Please think of our environment and only print this email if necessary.

_______________________________________________ Everybody mailing list -- everybody@acfr.usyd.edu.au To unsubscribe send an email to everybody-leave@acfr.usyd.edu.au